5 papers
Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists
Arnavi Chheda-Kothary, Lucy Lu Wang, Joseph Chee Chang +1
Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text. While blind or low-vision (BLV) scientists have tradi…
GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users
Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary +4
Geovisualizations are powerful tools for communicating spatial information, but are inaccessible to screen-reader users. To address this limitation, we present GeoVisA11y, an LLM-b…
OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
Jiacheng Liu, Taylor Blanton, Yanai Elazar +28
We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows ver…
ArtInsight: Enabling AI-Powered Artwork Engagement for Mixed Visual-Ability Families
Arnavi Chheda-Kothary, Ritesh Kanchi, Chris Sanders +5
We introduce ArtInsight, a novel AI-powered system to facilitate deeper engagement with child-created artwork in mixed visual-ability families. ArtInsight leverages large language…
AltGeoViz: Facilitating Accessible Geovisualization
Chu Li, Rock Yuren Pang, Ather Sharif +3
Geovisualizations are powerful tools for exploratory spatial analysis, enabling sighted users to discern patterns, trends, and relationships within geographic data. However, these…